1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
|
; NOTE: Assertions have been autogenerated by utils/update_test_checks.py UTC_ARGS: --check-globals none --version 6
; RUN: opt -p loop-vectorize -force-vector-width=4 -S %s | FileCheck %s
define void @call_loop_invariant_operand_bundle(ptr %dst, {float, float} %sv) {
; CHECK-LABEL: define void @call_loop_invariant_operand_bundle(
; CHECK-SAME: ptr [[DST:%.*]], { float, float } [[SV:%.*]]) {
; CHECK-NEXT: [[ENTRY:.*:]]
; CHECK-NEXT: br label %[[VECTOR_PH:.*]]
; CHECK: [[VECTOR_PH]]:
; CHECK-NEXT: [[TMP0:%.*]] = extractvalue { float, float } [[SV]], 0
; CHECK-NEXT: [[BROADCAST_SPLATINSERT:%.*]] = insertelement <4 x float> poison, float [[TMP0]], i64 0
; CHECK-NEXT: [[BROADCAST_SPLAT:%.*]] = shufflevector <4 x float> [[BROADCAST_SPLATINSERT]], <4 x float> poison, <4 x i32> zeroinitializer
; CHECK-NEXT: [[TMP1:%.*]] = extractvalue { float, float } [[SV]], 1
; CHECK-NEXT: [[BROADCAST_SPLATINSERT1:%.*]] = insertelement <4 x float> poison, float [[TMP1]], i64 0
; CHECK-NEXT: [[BROADCAST_SPLAT2:%.*]] = shufflevector <4 x float> [[BROADCAST_SPLATINSERT1]], <4 x float> poison, <4 x i32> zeroinitializer
; CHECK-NEXT: br label %[[VECTOR_BODY:.*]]
; CHECK: [[VECTOR_BODY]]:
; CHECK-NEXT: [[INDEX:%.*]] = phi i32 [ 0, %[[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], %[[VECTOR_BODY]] ]
; CHECK-NEXT: [[TMP2:%.*]] = getelementptr float, ptr [[DST]], i32 [[INDEX]]
; CHECK-NEXT: [[TMP3:%.*]] = call <4 x float> @llvm.pow.v4f32(<4 x float> [[BROADCAST_SPLAT]], <4 x float> [[BROADCAST_SPLAT2]]) [ "deopt"(float 1.000000e+01) ]
; CHECK-NEXT: store <4 x float> [[TMP3]], ptr [[TMP2]], align 4
; CHECK-NEXT: [[INDEX_NEXT]] = add nuw i32 [[INDEX]], 4
; CHECK-NEXT: [[TMP4:%.*]] = icmp eq i32 [[INDEX_NEXT]], 1000
; CHECK-NEXT: br i1 [[TMP4]], label %[[MIDDLE_BLOCK:.*]], label %[[VECTOR_BODY]], !llvm.loop [[LOOP0:![0-9]+]]
; CHECK: [[MIDDLE_BLOCK]]:
; CHECK-NEXT: br label %[[EXIT:.*]]
; CHECK: [[EXIT]]:
; CHECK-NEXT: ret void
;
entry:
br label %loop
loop:
%iv = phi i32 [ 0, %entry ], [ %iv.next, %loop ]
%a = extractvalue { float, float } %sv, 0
%b = extractvalue { float, float } %sv, 1
%addr = getelementptr float, ptr %dst, i32 %iv
%p = call float @llvm.pow.f32(float %a, float %b) [ "deopt"(float 10.0) ]
store float %p, ptr %addr
%iv.next = add nsw i32 %iv, 1
%cond = icmp ne i32 %iv.next, 1000
br i1 %cond, label %loop, label %exit
exit:
ret void
}
define void @call_unknown_operand_bundle(ptr %dst, {float, float} %sv) {
; CHECK-LABEL: define void @call_unknown_operand_bundle(
; CHECK-SAME: ptr [[DST:%.*]], { float, float } [[SV:%.*]]) {
; CHECK-NEXT: [[ENTRY:.*:]]
; CHECK-NEXT: br label %[[VECTOR_PH:.*]]
; CHECK: [[VECTOR_PH]]:
; CHECK-NEXT: [[TMP0:%.*]] = extractvalue { float, float } [[SV]], 0
; CHECK-NEXT: [[BROADCAST_SPLATINSERT:%.*]] = insertelement <4 x float> poison, float [[TMP0]], i64 0
; CHECK-NEXT: [[BROADCAST_SPLAT:%.*]] = shufflevector <4 x float> [[BROADCAST_SPLATINSERT]], <4 x float> poison, <4 x i32> zeroinitializer
; CHECK-NEXT: [[TMP1:%.*]] = extractvalue { float, float } [[SV]], 1
; CHECK-NEXT: [[BROADCAST_SPLATINSERT1:%.*]] = insertelement <4 x float> poison, float [[TMP1]], i64 0
; CHECK-NEXT: [[BROADCAST_SPLAT2:%.*]] = shufflevector <4 x float> [[BROADCAST_SPLATINSERT1]], <4 x float> poison, <4 x i32> zeroinitializer
; CHECK-NEXT: br label %[[VECTOR_BODY:.*]]
; CHECK: [[VECTOR_BODY]]:
; CHECK-NEXT: [[INDEX:%.*]] = phi i32 [ 0, %[[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], %[[VECTOR_BODY]] ]
; CHECK-NEXT: [[TMP2:%.*]] = getelementptr float, ptr [[DST]], i32 [[INDEX]]
; CHECK-NEXT: [[TMP3:%.*]] = call <4 x float> @llvm.pow.v4f32(<4 x float> [[BROADCAST_SPLAT]], <4 x float> [[BROADCAST_SPLAT2]]) [ "unknown"(ptr null) ]
; CHECK-NEXT: store <4 x float> [[TMP3]], ptr [[TMP2]], align 4
; CHECK-NEXT: [[INDEX_NEXT]] = add nuw i32 [[INDEX]], 4
; CHECK-NEXT: [[TMP4:%.*]] = icmp eq i32 [[INDEX_NEXT]], 1000
; CHECK-NEXT: br i1 [[TMP4]], label %[[MIDDLE_BLOCK:.*]], label %[[VECTOR_BODY]], !llvm.loop [[LOOP3:![0-9]+]]
; CHECK: [[MIDDLE_BLOCK]]:
; CHECK-NEXT: br label %[[EXIT:.*]]
; CHECK: [[EXIT]]:
; CHECK-NEXT: ret void
;
entry:
br label %loop
loop:
%iv = phi i32 [ 0, %entry ], [ %iv.next, %loop ]
%a = extractvalue { float, float } %sv, 0
%b = extractvalue { float, float } %sv, 1
%addr = getelementptr float, ptr %dst, i32 %iv
%p = call float @llvm.pow.f32(float %a, float %b) [ "unknown"(ptr null) ]
store float %p, ptr %addr
%iv.next = add nsw i32 %iv, 1
%cond = icmp ne i32 %iv.next, 1000
br i1 %cond, label %loop, label %exit
exit:
ret void
}
define void @call_cold_operand_bundle(ptr %dst, {float, float} %sv) {
; CHECK-LABEL: define void @call_cold_operand_bundle(
; CHECK-SAME: ptr [[DST:%.*]], { float, float } [[SV:%.*]]) {
; CHECK-NEXT: [[ENTRY:.*:]]
; CHECK-NEXT: br label %[[VECTOR_PH:.*]]
; CHECK: [[VECTOR_PH]]:
; CHECK-NEXT: [[TMP0:%.*]] = extractvalue { float, float } [[SV]], 0
; CHECK-NEXT: [[BROADCAST_SPLATINSERT:%.*]] = insertelement <4 x float> poison, float [[TMP0]], i64 0
; CHECK-NEXT: [[BROADCAST_SPLAT:%.*]] = shufflevector <4 x float> [[BROADCAST_SPLATINSERT]], <4 x float> poison, <4 x i32> zeroinitializer
; CHECK-NEXT: [[TMP1:%.*]] = extractvalue { float, float } [[SV]], 1
; CHECK-NEXT: [[BROADCAST_SPLATINSERT1:%.*]] = insertelement <4 x float> poison, float [[TMP1]], i64 0
; CHECK-NEXT: [[BROADCAST_SPLAT2:%.*]] = shufflevector <4 x float> [[BROADCAST_SPLATINSERT1]], <4 x float> poison, <4 x i32> zeroinitializer
; CHECK-NEXT: br label %[[VECTOR_BODY:.*]]
; CHECK: [[VECTOR_BODY]]:
; CHECK-NEXT: [[INDEX:%.*]] = phi i32 [ 0, %[[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], %[[VECTOR_BODY]] ]
; CHECK-NEXT: [[TMP2:%.*]] = getelementptr float, ptr [[DST]], i32 [[INDEX]]
; CHECK-NEXT: [[TMP3:%.*]] = call <4 x float> @llvm.pow.v4f32(<4 x float> [[BROADCAST_SPLAT]], <4 x float> [[BROADCAST_SPLAT2]]) [ "cold"() ]
; CHECK-NEXT: store <4 x float> [[TMP3]], ptr [[TMP2]], align 4
; CHECK-NEXT: [[INDEX_NEXT]] = add nuw i32 [[INDEX]], 4
; CHECK-NEXT: [[TMP4:%.*]] = icmp eq i32 [[INDEX_NEXT]], 1000
; CHECK-NEXT: br i1 [[TMP4]], label %[[MIDDLE_BLOCK:.*]], label %[[VECTOR_BODY]], !llvm.loop [[LOOP4:![0-9]+]]
; CHECK: [[MIDDLE_BLOCK]]:
; CHECK-NEXT: br label %[[EXIT:.*]]
; CHECK: [[EXIT]]:
; CHECK-NEXT: ret void
;
entry:
br label %loop
loop:
%iv = phi i32 [ 0, %entry ], [ %iv.next, %loop ]
%a = extractvalue { float, float } %sv, 0
%b = extractvalue { float, float } %sv, 1
%addr = getelementptr float, ptr %dst, i32 %iv
%p = call float @llvm.pow.f32(float %a, float %b) [ "cold"() ]
store float %p, ptr %addr
%iv.next = add nsw i32 %iv, 1
%cond = icmp ne i32 %iv.next, 1000
br i1 %cond, label %loop, label %exit
exit:
ret void
}
define void @assume_loop_variant_operand_bundle(ptr noalias %a, ptr noalias %b) {
; CHECK-LABEL: define void @assume_loop_variant_operand_bundle(
; CHECK-SAME: ptr noalias [[A:%.*]], ptr noalias [[B:%.*]]) {
; CHECK-NEXT: [[ENTRY:.*:]]
; CHECK-NEXT: br label %[[VECTOR_PH:.*]]
; CHECK: [[VECTOR_PH]]:
; CHECK-NEXT: br label %[[VECTOR_BODY:.*]]
; CHECK: [[VECTOR_BODY]]:
; CHECK-NEXT: [[INDEX:%.*]] = phi i64 [ 0, %[[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], %[[VECTOR_BODY]] ]
; CHECK-NEXT: [[TMP0:%.*]] = add i64 [[INDEX]], 0
; CHECK-NEXT: [[TMP1:%.*]] = add i64 [[INDEX]], 1
; CHECK-NEXT: [[TMP2:%.*]] = add i64 [[INDEX]], 2
; CHECK-NEXT: [[TMP3:%.*]] = add i64 [[INDEX]], 3
; CHECK-NEXT: [[TMP8:%.*]] = getelementptr inbounds float, ptr [[B]], i64 [[TMP0]]
; CHECK-NEXT: [[WIDE_LOAD:%.*]] = load <4 x float>, ptr [[TMP8]], align 4
; CHECK-NEXT: tail call void @llvm.assume(i1 true) [ "align"(ptr [[A]], i64 [[TMP0]]) ]
; CHECK-NEXT: tail call void @llvm.assume(i1 true) [ "align"(ptr [[A]], i64 [[TMP1]]) ]
; CHECK-NEXT: tail call void @llvm.assume(i1 true) [ "align"(ptr [[A]], i64 [[TMP2]]) ]
; CHECK-NEXT: tail call void @llvm.assume(i1 true) [ "align"(ptr [[A]], i64 [[TMP3]]) ]
; CHECK-NEXT: [[TMP5:%.*]] = fadd <4 x float> [[WIDE_LOAD]], splat (float 1.000000e+00)
; CHECK-NEXT: [[TMP10:%.*]] = getelementptr inbounds float, ptr [[A]], i64 [[TMP0]]
; CHECK-NEXT: store <4 x float> [[TMP5]], ptr [[TMP10]], align 4
; CHECK-NEXT: [[INDEX_NEXT]] = add nuw i64 [[INDEX]], 4
; CHECK-NEXT: [[TMP11:%.*]] = icmp eq i64 [[INDEX_NEXT]], 1600
; CHECK-NEXT: br i1 [[TMP11]], label %[[MIDDLE_BLOCK:.*]], label %[[VECTOR_BODY]], !llvm.loop [[LOOP5:![0-9]+]]
; CHECK: [[MIDDLE_BLOCK]]:
; CHECK-NEXT: br label %[[EXIT:.*]]
; CHECK: [[EXIT]]:
; CHECK-NEXT: ret void
;
entry:
br label %loop
loop:
%iv = phi i64 [ 0, %entry ], [ %iv.next, %loop ]
%arrayidx = getelementptr inbounds float, ptr %b, i64 %iv
%0 = load float, ptr %arrayidx, align 4
%cmp1 = fcmp ogt float %0, 1.000000e+02
tail call void @llvm.assume(i1 true) [ "align"(ptr %a, i64 %iv) ]
%add = fadd float %0, 1.000000e+00
%arrayidx5 = getelementptr inbounds float, ptr %a, i64 %iv
store float %add, ptr %arrayidx5, align 4
%iv.next = add nuw nsw i64 %iv, 1
%exitcond = icmp eq i64 %iv, 1599
br i1 %exitcond, label %exit, label %loop
exit:
ret void
}
define void @assume_cold_operand_bundle(ptr noalias %a, ptr noalias %b) {
; CHECK-LABEL: define void @assume_cold_operand_bundle(
; CHECK-SAME: ptr noalias [[A:%.*]], ptr noalias [[B:%.*]]) {
; CHECK-NEXT: [[ENTRY:.*:]]
; CHECK-NEXT: br label %[[VECTOR_PH:.*]]
; CHECK: [[VECTOR_PH]]:
; CHECK-NEXT: tail call void @llvm.assume(i1 true) [ "cold"() ]
; CHECK-NEXT: br label %[[VECTOR_BODY:.*]]
; CHECK: [[VECTOR_BODY]]:
; CHECK-NEXT: [[INDEX:%.*]] = phi i64 [ 0, %[[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], %[[VECTOR_BODY]] ]
; CHECK-NEXT: [[TMP0:%.*]] = getelementptr inbounds float, ptr [[B]], i64 [[INDEX]]
; CHECK-NEXT: [[WIDE_LOAD:%.*]] = load <4 x float>, ptr [[TMP0]], align 4
; CHECK-NEXT: [[TMP1:%.*]] = fadd <4 x float> [[WIDE_LOAD]], splat (float 1.000000e+00)
; CHECK-NEXT: [[TMP2:%.*]] = getelementptr inbounds float, ptr [[A]], i64 [[INDEX]]
; CHECK-NEXT: store <4 x float> [[TMP1]], ptr [[TMP2]], align 4
; CHECK-NEXT: [[INDEX_NEXT]] = add nuw i64 [[INDEX]], 4
; CHECK-NEXT: [[TMP3:%.*]] = icmp eq i64 [[INDEX_NEXT]], 1600
; CHECK-NEXT: br i1 [[TMP3]], label %[[MIDDLE_BLOCK:.*]], label %[[VECTOR_BODY]], !llvm.loop [[LOOP6:![0-9]+]]
; CHECK: [[MIDDLE_BLOCK]]:
; CHECK-NEXT: br label %[[EXIT:.*]]
; CHECK: [[EXIT]]:
; CHECK-NEXT: ret void
;
entry:
br label %loop
loop:
%iv = phi i64 [ 0, %entry ], [ %iv.next, %loop ]
%arrayidx = getelementptr inbounds float, ptr %b, i64 %iv
%0 = load float, ptr %arrayidx, align 4
%cmp1 = fcmp ogt float %0, 1.000000e+02
tail call void @llvm.assume(i1 true) [ "cold"() ]
%add = fadd float %0, 1.000000e+00
%arrayidx5 = getelementptr inbounds float, ptr %a, i64 %iv
store float %add, ptr %arrayidx5, align 4
%iv.next = add nuw nsw i64 %iv, 1
%exitcond = icmp eq i64 %iv, 1599
br i1 %exitcond, label %exit, label %loop
exit:
ret void
}
|
